Estimativa da radiação solar ultravioleta em Botucatu/SP/Brasil utilizando máquina de vetores de suporte (SVM)

• Autor(a) principal: Almeida, Thiago do Nascimento Santana de [UNESP]
• Data de Publicação: 2013
• Outros Autores: Teramoto, Érico Tadao [UNESP], Pai, Alexandre Dal, Rodrigues, Douglas [UNESP], Escobedo, João Francisco [UNESP]
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://www.fatecbt.edu.br/seer/index.php/tl/article/view/165; http://hdl.handle.net/11449/140788
• topic: Machine learning; Estimative models; Support vector machine; Aprendizado de máquina; Modelos de estimativa; Support vector machin

In this papper is evaluated the estimation of daily solar ultraviolet radiation (UV) using Support Vector Machine (SVM) in Botucatu/SP/Brazil. We tested five groups of input data containing different weather variables. A more precise estimation of UV was obtained using insolation data, relative humidity, air temperature, precipitation, photoperiod, solar radiation at the top of the atmosphere, ultraviolet radiation at the top of the atmosphere, solar radiation global, clearness index kt and relative optical mass as input variables. This model had MBE = -0,99%; RMSE = 6,58%, d = 0,989 and R² = 0.960, equivalent performance those found in the literature.